A2a Auditor runs on your own machine — the client starts it, so there is no endpoint to ping. 39 installs a week from npm. Last commit 11 Oct 2026.
Scans Agent2Agent (A2A) protocol code for webhook SSRF, missing auth, and credential exposure
Today is the operative word: we check A2a Auditor every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add a2a-auditor -- npx -y @guardbee/mcp-a2a-auditor
{
"mcpServers": {
"a2a-auditor": {
"args": [
"-y",
"@guardbee/mcp-a2a-auditor"
],
"command": "npx"
}
}
}
[mcp_servers.a2a-auditor]
command = "npx"
args = ["-y", "@guardbee/mcp-a2a-auditor"]
{
"mcpServers": {
"a2a-auditor": {
"args": [
"-y",
"@guardbee/mcp-a2a-auditor"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"a2a-auditor": {
"args": [
"-y",
"@guardbee/mcp-a2a-auditor"
],
"command": "npx"
}
}
}
Scans MCP server auth code for OAuth 2.1 anti-patterns: token passthrough, missing audience
Scans MCP server auth code for OAuth 2.1 anti-patterns: token passthrough, missing audience
Security audit for AI agents: code, deps, exposure, secrets, drift, SBOM, and IoC.
Create and manage secure sandboxes for running AI agent code
Dynamic QR codes for AI agents — custom styling, scan tracking, webhooks
Scans code, IaC and AI-agent config for security problems. Read-only — nothing can be edited.
Scans agent code for untrusted input poisoning persistent cross-session memory
Scan any codebase, generate CONVENTIONS.md, expose conventions as MCP tools for AI agents.
Answers built from our own checks of this server.